Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    real

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    κά
    -0.07
     Generic
    -0.07
    فاق
    -0.07
     hiểu
    -0.06
    erro
    -0.06
     generic
    -0.06
     conservative
    -0.06
    -state
    -0.06
     serializers
    -0.06
     계
    -0.06
    POSITIVE LOGITS
     Asi
    0.07
    (info
    0.06
    .functional
    0.06
     amounted
    0.06
     أخ
    0.06
    ाई
    0.06
    .norm
    0.06
     flesh
    0.06
    ﾆ
    0.06
     often
    0.06
    Act Density 0.047%

    No Known Activations